Continual Spatio-Temporal Graph Convolutional Networks

Lukas Hedegaard Morsing, Negar Heidari, Alexandros Iosifidis

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Abstract

Graph-based reasoning over skeleton data has emerged as a promising approach for human action recognition. However, the application of prior graph-based methods, which predominantly employ whole temporal sequences as their input, to the setting of online inference entails considerable computational redundancy. In this paper, we tackle this issue by reformulating the Spatio-Temporal Graph Convolutional Neural Network as a Continual Inference Network, which can perform step-by-step predictions in time without repeat frame processing. To evaluate our method, we create a continual version of ST-GCN, CoST-GCN, alongside two derived methods with different self-attention mechanisms, CoAGCN and CoS-TR. We investigate weight transfer strategies and architectural modifications for inference acceleration, and perform experiments on the NTU RGB+D 60, NTU RGB+D 120, and Kinetics Skeleton 400 datasets. Retaining similar predictive accuracy, we observe up to 109× reduction in time complexity, on-hardware accelerations of 26×, and reductions in maximum allocated memory of 52% during online inference.

Original languageEnglish
Article number109528
JournalPattern Recognition
Volume140
IssueC
Number of pages11
ISSN0031-3203
DOIs
Publication statusPublished - Aug 2023

Keywords

  • Continual inference
  • Efficient deep learning
  • Graph convolutional networks
  • Skeleton-based action recognition

Fingerprint

Dive into the research topics of 'Continual Spatio-Temporal Graph Convolutional Networks'. Together they form a unique fingerprint.

Cite this